Automated identification of individual birds by song enables multi-year recapture from passive acoustic monitoring data

Abstract

Autonomous sensors and machine learning are transforming ecology by enabling large-scale observation of organisms and ecosystems. However, sensor data collected by camera traps, acoustic recorders, and satellites are typically used only to produce detections of unidentified individuals. Tracking individuals over time to study movement, survival, and behavior continues to require invasive and high-effort capture and marking techniques. Here, we introduce an automated, general approach that identifies individual animals from passive acoustic recordings based on individually distinctive vocalizations. Unlike previous approaches, ours can identify individuals in passive acoustic recordings without previously labeled examples of their vocalizations. We apply our approach to a model songbird species (Ovenbird, Seiurus aurocapilla), estimating abundance and annual survival across 126 locations and four years. Our approach identifies individuals with 96% accuracy. We find high Ovenbird apparent annual survival (0.70) and acoustic recapture probability (0.89) across 405 individuals. Our approach can readily be applied to other species with individually distinctive vocalizations using open-source Python implementations. Automated individual identification will broadly unlock the ability to passively recapture individual animals at the massive scale of autonomous sensing, supporting the study of population trajectories and informing proactive ecosystem management to prevent biodiversity loss.